1 Setup
2 Raw data
- 2.1 Quality Control
- 2.2 Export
3 Data normalisation
4 PCA of only TEs (subsetted data)
- 4.1 2D
  - 4.1.1 Heatmap
- 4.2 Conclusion
5 Session Info

1 Setup

Libraries

suppressPackageStartupMessages({
  library(data.table)
  library(DESeq2)
  library(gplots)
  library(here)
  library(hyperSpec)
  library(parallel)
  library(pander)
  library(plotly)
  library(tidyverse)
  library(tximport)
  library(vsn)
})

Helper functions

source(here("UPSCb-common/src/R/featureSelection.R"))

Graphics

hpal <- colorRampPalette(c("blue","white","red"))(100)

Metadata Sample information

samples <- read_csv(here("doc/samples_final.csv"))

## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   ScilifeID = col_character(),
##   SubmittedID = col_character(),
##   Stages = col_character(),
##   Description = col_character(),
##   ID = col_character()
## )

2 Raw data

filelist <- list.files(here("data/salmon"), 
                          recursive = TRUE, 
                          pattern = "quant.sf",
                          full.names = TRUE)

Sanity check to ensure that the data is sorted according to the sample info

filelist <- filelist[match(samples$ScilifeID,sub("_sortmerna.*","",basename(dirname(filelist))))]

stopifnot(all(match(sub("_sortmerna.*","",basename(dirname(filelist))),
                    samples$ScilifeID) == 1:nrow(samples)))

name the file list vector

names(filelist) <- samples$ID

Read the expression at the gene level

counts <- suppressMessages(round(tximport(files = filelist, 
                                          type = "salmon",
                                          txOut=TRUE)$counts))

combine technical replicates

samples$ID <- sub("_L00[1,2]", "",
                  samples$ScilifeID)
counts <- do.call(
  cbind,
  lapply(split.data.frame(t(counts),
                          samples$ID),
         colSums))

csamples <- samples[,-1]
csamples <- csamples[match(colnames(counts),csamples$ID),]

2.1 Quality Control

Check how many genes are never expressed

sel <- rowSums(counts) == 0
sprintf("%s%% percent (%s) of %s genes are not expressed",
        round(sum(sel) * 100/ nrow(counts),digits=1),
        sum(sel),
        nrow(counts))

## [1] "19.8% percent (13135) of 66360 genes are not expressed"

Let us take a look at the sequencing depth, colouring by Stages.

dat <- tibble(x=colnames(counts),y=colSums(counts)) %>% 
  bind_cols(csamples)

ggplot(dat,aes(x,y,fill=csamples$Stages)) + geom_col() + 
  scale_y_continuous(name="reads") +
  theme(axis.text.x=element_text(angle=90,size=4),axis.title.x=element_blank())

Display the per-gene mean expression

i.e. the mean raw count of every gene across samples is calculated and displayed on a log10 scale.

The cumulative gene coverage is as expected

ggplot(data.frame(value=log10(rowMeans(counts))),aes(x=value)) + 
  geom_density() + ggtitle("gene mean raw counts distribution") +
  scale_x_continuous(name="mean raw counts (log10)")

## Warning: Removed 13135 rows containing non-finite values (stat_density).

The same is done for the individual samples colored by Stages.

dat <- as.data.frame(log10(counts)) %>% utils::stack() %>% 
  mutate(Stages=csamples$Stages[match(ind,csamples$ID)])

ggplot(dat,aes(x=values,group=ind,col=Stages)) + 
  geom_density() + ggtitle("sample raw counts distribution") +
  scale_x_continuous(name="per gene raw counts (log10)")

## Warning: Removed 622137 rows containing non-finite values (stat_density).

2.2 Export

dir.create(here("data/analysis/salmon"),showWarnings=FALSE,recursive=TRUE)
write.csv(counts,file=here("data/analysis/salmon/raw-unormalised-gene-expression_data_genes+TEs.csv"))

3 Data normalisation

3.1 Preparation

For visualization, the data is submitted to a variance stabilization transformation using DESeq2. The dispersion is estimated independently of the sample tissue and replicate.

csamples$Stages <- factor(csamples$Stages)

dds <- DESeqDataSetFromMatrix(
  countData = counts,
  colData = csamples,
  design = ~Stages)

## converting counts to integer mode

save(dds,file=here("data/analysis/salmon/dds_genes_TEs.rda"))

Check the size factors (i.e. the sequencing library size effect)

dds <- estimateSizeFactors(dds)
sizes <- sizeFactors(dds)
pander(sizes)

Table continues below
P7614_301_S1	P7614_302_S2	P7614_303_S3	P7614_304_S4	P7614_305_S5
0.997	0.9789	1.096	1.053	1.102

Table continues below
P7614_306_S6	P7614_307_S7	P7614_308_S8	P7614_309_S9	P7614_310_S10
1.311	1.091	1.167	0.9277	0.8292

Table continues below
P7614_311_S11	P7614_312_S12	P7614_313_S13	P7614_314_S14	P7614_315_S15
0.918	0.8462	1.007	0.9453	1.102

Table continues below
P7614_316_S16	P7614_317_S17	P7614_318_S18	P7614_319_S19	P7614_320_S20
1.01	0.9052	0.9999	0.9703	0.9241

P7614_321_S21	P7614_322_S22	P7614_323_S23	P7614_324_S24
1.119	1.072	0.9857	0.9988

boxplot(sizes, main="Sequencing libraries size factor")

3.2 Variance Stabilising Transformation

vsd <- varianceStabilizingTransformation(dds, blind=TRUE)
vst <- assay(vsd)
vst <- vst - min(vst)
save(vst,file=here("data/analysis/DE/vst-blind_genes_TEs.rda"))

3.3 Variance Stabilising Transformation

vsda <- varianceStabilizingTransformation(dds, blind=FALSE)
vsta <- assay(vsda)
vsta <- vsta - min(vsta)
save(vsta,file=here("data/analysis/DE/vst-aware_genes_TEs.rda"))

# prepare the data to build the network
#ID <- rownames(vsta)
#vsta <- cbind(ID,vsta)
#vsta_tibble <- as_tibble(vsta)
#write_tsv(vsta_tibble,path=here("data/analysis/DE/vst-aware_genes+TEs.tsv"))

Validation

The variance stabilisation worked adequately

meanSdPlot(vsta[rowSums(vsta)>0,])

3.4 QC on the normalised data

3.4.1 PCA

load(here("data/analysis/salmon/dds_genes_TEs.rda"))
load(here("data/analysis/DE/vst-aware_genes_TEs.rda"))
pc <- prcomp(t(vsta))
percent <- round(summary(pc)$importance[2,]*100)

Cumulative components effect

We define the number of variable of the model

nvar=1

An the number of possible combinations

nlevel=nlevels(dds$Stages)

We plot the percentage explained by the different components, the red line represent the number of variable in the model, the orange line the number of variable combinations.

ggplot(tibble(x=1:length(percent),y=cumsum(percent)),aes(x=x,y=y)) +
  geom_line() + scale_y_continuous("variance explained (%)",limits=c(0,100)) +
  scale_x_continuous("Principal component") + 
  geom_vline(xintercept=nvar,colour="red",linetype="dashed",size=0.5) + 
  geom_hline(yintercept=cumsum(percent)[nvar],colour="red",linetype="dashed",size=0.5) +
  geom_vline(xintercept=nlevel,colour="orange",linetype="dashed",size=0.5) + 
  geom_hline(yintercept=cumsum(percent)[nlevel],colour="orange",linetype="dashed",size=0.5)

3.4.2 2D

pc.dat <- bind_cols(PC1=pc$x[,1],
                    PC2=pc$x[,2],
                    csamples)

p <- ggplot(pc.dat,aes(x=PC2,y=PC1,col=Stages,text=dds$ID)) + 
  geom_point(size=2) + 
  ggtitle("Principal Component Analysis")
          #,subtitle="variance stabilized counts") 

plot(p + labs(x=paste("PC2 (",percent[2],"%)",sep=""),
              y=paste("PC1 (",percent[1],"%)",sep="")))

ggplotly(p) %>% 
  layout(xaxis=list(title=paste("PC2 (",percent[2],"%)",sep="")),
         yaxis=list(title=paste("PC1 (",percent[1],"%)",sep="")))

3.4.3 Heatmap

Filter for noise

conds <- factor(csamples$Stages)
sels <- rangeFeatureSelect(counts=vsta,
                           conditions=conds,
                           nrep=3)

## Warning in xy.coords(x, y, xlabel, ylabel, log): 1 y value <= 0 omitted from
## logarithmic plot

vst.cutoff <- 1

Heatmap of “all” genes

hm <- heatmap.2(t(scale(t(vsta[sels[[vst.cutoff+1]],]))),
          distfun=pearson.dist,
          hclustfun=function(X){hclust(X,method="ward.D2")},
          labRow = NA,trace = "none",
          labCol = conds,
          col=hpal)

plot(as.hclust(hm$colDendrogram),xlab="",sub="",labels=conds)

Biological QA only on TEs

#load(here("data/analysis/DE/vst-aware_genes_TEs.rda"))
TEs <- vsta[grepl("^MA_", rownames(vsta)) == FALSE, ]

4 PCA of only TEs (subsetted data)

pc_TEs <- prcomp(t(vsta[grepl("^MA_", rownames(vsta)) == FALSE, ]))
percent_TEs <- round(summary(pc_TEs)$importance[2,]*100)

4.1 2D

pc.dat_TEs <- bind_cols(PC1=pc_TEs$x[,1],
                    PC2=pc_TEs$x[,2],
                    csamples)

p <- ggplot(pc.dat_TEs,aes(x=PC1,y=PC2,col=Stages,text=dds$ID)) + 
  geom_point(size=2) + 
  ggtitle("Principal Component Analysis",subtitle="variance stabilized counts")

ggplotly(p) %>% 
  layout(xaxis=list(title=paste("PC1 (",percent_TEs[1],"%)",sep="")),
         yaxis=list(title=paste("PC2 (",percent_TEs[2],"%)",sep="")))

4.1.1 Heatmap